Indra Kumar Shah

Indra Kumar Shah

Auto-generated profile, based on publicly available information

Indra Kumar Shah

Department of Ai and big data, Woosong University, Daejeon, south korea

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 July 2022 in IEEE Access
Verified
Journal Article
Open access
ISIndra Kumar Shah
Indra Kumar Shah
TMTanmoy Maity
Tanmoy Maity
YDYogendra Singh Dohare
Yogendra Singh Dohare
DTDevvrat Tyagi
Devvrat Tyagi
DRDeepak Rathore
Deepak Rathore
DYDharmendra Singh Yadav
Dharmendra Singh Yadav
Energy minimization is one of the paramount issues in designing of the wireless sensor network and becomes more complex for multi-hop transmission. Furthermore, selection of multi hop route for the packets transmission is also a tedious task. In this paper, we propose an intra-cluster and inter-cluster (ICIC) energy minimization strategy for multihop wireless sensor network (WSN). In the proposed strategy, in intra cluster communication, a dynamic duty cycle allocation based on the cluster head (CH) node distance from the child nodes for the energy minimization is presented. In the inter cluster communication, minimum energy consumption route is chosen for the transmission of packets to base station (BS). The proposed strategy is compared with four state of the art techniques i.e., HEEMP, LEACH, MLEACH, and SEP protocols of clustering. The evaluation of the proposed and existing strategies is done in two different scenarios i.e., number of round and number of nodes. Results of the simulation show that the proposed strategy transmits more packets and has lower number of dead nodes than other strategies. Furthermore, proposed strategy utilizes more network energy and more energy for relaying.

11 March 2025 in IEEE Access
Verified
Journal Article
Open access
JDJayameena Desikan
Jayameena Desikan
SSSushil Kumar Singh
Sushil Kumar Singh
AJA. Jayanthiladevi
A. Jayanthiladevi
SSSaurabh Singh
Saurabh Singh
Byungun YoonByungun Yoon
Byungun Yoon
In high-risk IoT-enabled Industrial Environments such as oil and gas industries, early and accurate fire detection is crucial to prevent catastrophic damage. Traditional fire detection systems that rely on single IoT sensors, like heat or smoke detectors, are prone to inaccuracies and delayed responses, particularly in noisy or complex industrial environments. This research proposes an advanced fire prediction approach aiming to enhance decision-making accuracy with uncertain or incomplete fire sensor data in an edge computing IoT complex industrial environment that integrates multiple supervised machine learning algorithms for each sensor types and Dempster-Shafer theory (DST) with multi-sensor fusion. By combining data from multiple different types of sensors (RGB, thermal, gas, smoke, and flame), the proposed architecture enhances the reliability of fire prediction and detection as each sensor detects different parameters of a fire and this ensures every parameter is considered for fire detection ensuring early detection and it reduces false positives. By preprocessing sensor data and by combining machine learning algorithms (MobileNet, EfficientNet, Random Forest, SVM, and Decision Trees) where each ML processes different sensor data types, this supports providing more accurate data to DST. The D-S theory helps in handling uncertainty by fusing conflicting multi-sensor data to generate a more reliable decision. The results demonstrate that this multiintegrated methodology proposed significantly outperforms traditional methods in predicting and detecting fires early and accurately, even under challenging and complex environmental conditions of Oil and Gas Industries. The goal of this research contribute to the development of advanced fire prediction protocols offering a robust solution for managing and mitigating fire risks in dynamic, data-rich IoT environments. Predicting fire and reducing Fire in a critical oil and gas IoT industrial environment remains a critical challenge. The proposed method aims to enhance fire prediction and detection accuracy through algorithms developed using sensor preprocessing, machine learning, and Dempster Shafer fusion handling uncertain and varying multi-sensor data and demonstrates real-time, data-driven decision-making in critical industrial environments. The results show an accuracy of 98.2%, a precision of 98.5%, and a recall of 98.3% significantly confirming the prediction over other models.

23 April 2025 in IEEE Access
Verified
Journal Article
Open access
VGVARUN GUPTA
VARUN GUPTA
VKVivek Kumar
Vivek Kumar
PKPrince Kumar
Prince Kumar
SSSaurabh Singh
Saurabh Singh
YLYoung-Seok Lee
Young-Seok Lee
IRIn-Ho Ra
In-Ho Ra
To analyze the physiological information within the acquired EEG signal is very cumbersome due to the possibility of several factors, viz. noise and artifacts, complexity of brain dynamics, and inter-subject variability. To address these issues, this paper compares a U-shaped encoder-decoder network (UNET) and Bat-based UNET signal analysis (BUSA) techniques to classify depression rates in the Electroencephalogram (EEG) datasets. The main objective of including these two techniques is to reveal their effectiveness. It comprises pre-processing, feature extraction, feature selection, and classification stages. The framework excels at noise reduction during pre-processing, enhancing dataset integrity. Feature extraction leverages band power and correlation dimension to extract crucial features. Furthermore, feature selection optimizes classification accuracy by refining the fitness function of bats in the classification layer. The performance of UNET and BUSA are compared based on the following performance evaluating parameters viz. accuracy (Acc), Area Under the Curve (AUC), precision (P), and recall (R) (or sensitivity (Se)). The results indicated that the BUSA technique outperforms the UNET technique.

11 August 2024 in Internet Technology Letters
Verified
Journal Article
Closed access
ISIndra Kumar Shah
Indra Kumar Shah
NRNeha Singh Rathaur
Neha Singh Rathaur
YDYogendra Singh Dohare
Yogendra Singh Dohare
TMTanmoy Maity
Tanmoy Maity

31 December 2024 in IEEE Access
Verified
Journal Article
Open access
GRgousia habib rather
gousia habib rather
IMIshfaq Ahmad Malik
Ishfaq Ahmad Malik
SQShaima Qureshi
Shaima Qureshi
IRIn-Ho Ra
In-Ho Ra
SSSaurabh Singh
Saurabh Singh
SSSurbhi Sharma
Surbhi Sharma
In the fields of healthcare and medical research, the analysis of biomedical images is of paramount importance. While conventional techniques like convolutional neural networks (CNNs) have been extensively employed for medical image examination, they often fall short in their ability to comprehend intricate spatial and contextual associations within biomedical data, especially in brain MRI scans. These shortcomings have prompted researchers to investigate more sophisticated approaches aimed at enhancing precision and adaptability. This research introduces an innovative method for analyzing brain MRI scans using Vision Transformers (ViTs), addressing the shortcomings of traditional convolutional neural networks (CNNs) in capturing complex spatial and contextual relationships. The primary aim is to enhance the generalization capabilities of biomedical image models by implementing a Shifted Patching Technique (S.P.T.) in conjunction with conventional non-overlapping patching. The proposed model is tested on the BRAIN MRI dataset, with image resolution standardized through novel Lancoz5 interpolation. The model’s effectiveness is further assessed using two additional datasets: ChestX-ray14 and Camelyon17. Performance evaluation metrics include accuracy, F1-score, and precision, while ablation studies are conducted to assess the contribution of individual architectural components. Findings indicate that the proposed ViT model surpasses traditional CNN-based approaches, demonstrating improved accuracy and versatility in brain MRI analysis and other medical imaging tasks. This study presents a more efficient tool for biomedical image analysis, with potential implications for medical research and diagnostic healthcare applications.

18 June 2021
Verified
Book Chapter
Closed access
PDF file
ISIndra Kumar Shah
Indra Kumar Shah
YDYogendra Singh Dohare
Yogendra Singh Dohare
TMTanmoy Maity
Tanmoy Maity
<!----> <!----> The advancement of wireless networking technology made the life of people simpler and more comfortable. Some of the most relevant facilities are remotely monitoring, diagnosing, and treating patients without being present at health facility centers. Due to the advancement of Very Large-Scale Integration (VLSI) technology, sensor systems are flexible and small in size, therefore it is easy to place them on or off the body. Such sensor systems are also capable of transmitting physiological data over the wireless medium to remote location servers or health centers. This remote communication technology is known as Wireless Body Area Network (WBAN). This article presents a comprehensive survey on architecture, various communication technologies, applications, and challenges of WBAN. We also present a comparison between the Wireless Sensor Network (WSN) and WBAN. <!----> <!---->